© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 38723
    Prev
    Next
    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    makeText
    -0.61
    own
    -0.55
    ,
    -0.55
    de
    -0.54
    DebuggerNonUser
    -0.52
     to
    -0.51
    now
    -0.50
    nya
    -0.50
     []:
    -0.50
    jgl
    -0.50
    POSITIVE LOGITS
     been
    0.75
    NewUrlParser
    0.66
    ритори
    0.66
    been
    0.66
     BEEN
    0.64
     AppColors
    0.63
    Been
    0.62
     Been
    0.61
    toyage
    0.59
     särskilt
    0.59
    Activations Density 0.141%

    No Known Activations